MiniMax models
14 MiniMax models you can call through MartLLM’s OpenAI-compatible API. The cheapest is MiniMax M2.1 at $0.00036/1M input tokens, as of November 20, 2026. Every request is routed to the cheapest healthy seller; the price shown has no MartLLM fee added.
- MiniMax M3.1 Flashminimax/minimax-m3-1-flash$0.0102 in$0.0410 out−93%
- MiniMax M3minimax/minimax-m3$0.0230 in$0.0920 out−92%
- MiniMax M2.5minimax/minimax-m2.5$0.0027 in$0.0094 out−99%
- MiniMax M2minimax/minimax-m2$0.0023 in$0.0093 out−99%
- MiniMax Speech 02 HD TTSminimax/tts-minimax-speech-02-hd$0.0813 per 1K characters−35%
- MiniMax M2.7minimax/minimax-m2.7$0.0244 in$0.0857 out−94%
- MiniMax M2.1minimax/minimax-m2.1$0.00036 in$0.0014 out
- MiniMax M3 Previewminimax/minimax-m3-preview$0.2170 in$0.8680 out−28%
- MiniMax M2.7 Highspeedminimax/minimax-m2.7-highspeed$0.1740 in$0.6960 out
- MiniMax H3minimax/minimax-h3$0.042 / sec
- MiniMax H3 Referenceminimax/minimax-h3-reference-to-video$0.042 / sec
- Hailuo 2.3 Standardminimax/hailuo-2-3-standard-image-to-video$0.0262 / sec
- Hailuo 2.3 Prominimax/hailuo-2-3-pro-image-to-video$0.0473 / sec
- Hailuo 02 Prominimax/hailuo-02-pro$0.0499 / sec−38%
| Model | Price (from) | Context | Type | Capabilities |
|---|---|---|---|---|
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.0102 in$0.0410 out−93% | 1000K | Text | ToolsReasoningVision |
| MiniMax M3 minimax/minimax-m3 | $0.0230 in$0.0920 out−92% | 200K | Text | ToolsVisionJSON |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0027 in$0.0094 out−99% | 198K | Text | ToolsReasoningJSON |
| MiniMax M2 minimax/minimax-m2 | $0.0023 in$0.0093 out−99% | 1000K | Text | ToolsJSON |
| MiniMax Speech 02 HD TTS minimax/tts-minimax-speech-02-hd | $0.0813 per 1K characters−35% | Audio | JSON | |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0244 in$0.0857 out−94% | 198K | Text | ToolsReasoningJSON |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 in$0.0014 out | 198K | Text | ToolsReasoningJSON |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.2170 in$0.8680 out−28% | 524K | Text | ToolsReasoningVision |
| MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed | $0.1740 in$0.6960 out | 205K | Text | ToolsJSON |
| MiniMax H3 minimax/minimax-h3 | $0.042 / sec | Video | Vision | |
| MiniMax H3 Reference minimax/minimax-h3-reference-to-video | $0.042 / sec | Video | Vision | |
| Hailuo 2.3 Standard minimax/hailuo-2-3-standard-image-to-video | $0.0262 / sec | Video | Vision | |
| Hailuo 2.3 Pro minimax/hailuo-2-3-pro-image-to-video | $0.0473 / sec | Video | Vision | |
| Hailuo 02 Pro minimax/hailuo-02-pro | $0.0499 / sec−38% | Video | Vision |
MiniMax models — FAQ
What is the cheapest MiniMax model?
MiniMax M2.1 is the cheapest MiniMax model on MartLLM right now, at $0.00036/1M input tokens. MartLLM routes each request to the cheapest healthy seller and bills the price shown, with no MartLLM fee added.
How many MiniMax models can I use through MartLLM?
14 MiniMax models are on the MartLLM marketplace today. One OpenAI-compatible API key and base URL (https://api.martllm.com/v1) calls every one of them — no per-provider contracts.
How do I call a MiniMax model with the API?
Use any OpenAI-compatible SDK: set the base URL to https://api.martllm.com/v1, your MartLLM key, and the model id (for example "minimax/minimax-m3-1-flash"). Anthropic SDKs work against https://api.martllm.com/v1/messages.